Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks

Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks

Paper in proceedings (conference paper)

The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-theart segmentation convolutional neural network architectures are very memory demanding, large batch size is often impossible to achieve on current hardware. We evaluate the alternative normalization methods proposed to solve this issue on a problem of binary spine segmentation from 3D CT scan. Our results show the effectiveness of Instance Normalization in the limited batch size neural network training environment. Out of all the compared methods the Instance Normalization achieved the highest result with Dice coefficient = 0.96 which is comparable to our previous results achieved by deeper network with longer training time. We also show that the Instance Normalization implementation used in this experiment is computational timeefficient when compared to the network without any normalization method.

The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-theart segmentation convolutional neural network architectures are very memory demanding, large batch size is often impossible to achieve on current hardware. We evaluate the alternative normalization methods proposed to solve this issue on a problem of binary spine segmentation from 3D CT scan. Our results show the effectiveness of Instance Normalization in the limited batch size neural network training environment. Out of all the compared methods the Instance Normalization achieved the highest result with Dice coefficient = 0.96 which is comparable to our previous results achieved by deeper network with longer training time. We also show that the Instance Normalization implementation used in this experiment is computational timeefficient when compared to the network without any normalization method.

Batch Normalization; Comparison; Group Normalization; Instance Normalization; Segmentation

Batch Normalization; Comparison; Group Normalization; Instance Normalization; Segmentation

KOLAŘÍK, M.; BURGET, R.; ŘÍHA, K.

2021

09.07.2020

978-1-7281-6376-5

2020 43rd International Conference on Telecommunications and Signal Processing (TSP)

677

680

4

https://ieeexplore.ieee.org/document/9163397